Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations

• URL: http://arxiv.org/abs/2503.18817v1
• Date: Mon, 24 Mar 2025 16:00:21 GMT
• Title: Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations
• Authors: Jeonghyeon Kim, Sangheum Hwang,
• Abstract summary: We show that multi-modal fine-tuning can achieve notable OoDD performance.<n>We propose a training objective that enhances cross-modal alignment by regularizing the distances between image and text embeddings of ID data.
• Score: 2.992602379681373
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prior research on out-of-distribution detection (OoDD) has primarily focused on single-modality models. Recently, with the advent of large-scale pretrained vision-language models such as CLIP, OoDD methods utilizing such multi-modal representations through zero-shot and prompt learning strategies have emerged. However, these methods typically involve either freezing the pretrained weights or only partially tuning them, which can be suboptimal for downstream datasets. In this paper, we highlight that multi-modal fine-tuning (MMFT) can achieve notable OoDD performance. Despite some recent works demonstrating the impact of fine-tuning methods for OoDD, there remains significant potential for performance improvement. We investigate the limitation of na\"ive fine-tuning methods, examining why they fail to fully leverage the pretrained knowledge. Our empirical analysis suggests that this issue could stem from the modality gap within in-distribution (ID) embeddings. To address this, we propose a training objective that enhances cross-modal alignment by regularizing the distances between image and text embeddings of ID data. This adjustment helps in better utilizing pretrained textual information by aligning similar semantics from different modalities (i.e., text and image) more closely in the hyperspherical representation space. We theoretically demonstrate that the proposed regularization corresponds to the maximum likelihood estimation of an energy-based model on a hypersphere. Utilizing ImageNet-1k OoD benchmark datasets, we show that our method, combined with post-hoc OoDD approaches leveraging pretrained knowledge (e.g., NegLabel), significantly outperforms existing methods, achieving state-of-the-art OoDD performance and leading ID accuracy.

Related papers

• Directional Gradient Projection for Robust Fine-Tuning of Foundation Models [25.04763038570959]
  Directional Gradient Projection (DiGraP) is a layer-wise trainable method that incorporates directional information from gradients to bridge regularization and multi-objective optimization. We first bridge the uni-modal and multi-modal gap by performing analysis on Image Classification reformulated Visual Question Answering (VQA) benchmarks. Experimental results show that DiGraP consistently outperforms existing baselines across Image Classfication and VQA tasks with discriminative and generative backbones.
  arXiv  Detail & Related papers  (2025-02-21T19:31:55Z)
• USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation [24.90512145836643]
  We introduce a Unified Skeleton-based Dense Representation Learning framework based on feature decorrelation.<n>We show that our approach significantly outperforms the current state-of-the-art (SOTA) approaches.
  arXiv  Detail & Related papers  (2024-12-12T12:20:27Z)
• A Bayesian Approach to Data Point Selection [24.98069363998565]
  Data point selection (DPS) is becoming a critical topic in deep learning. Existing approaches to DPS are predominantly based on a bi-level optimisation (BLO) formulation. We propose a novel Bayesian approach to DPS.
  arXiv  Detail & Related papers  (2024-11-06T09:04:13Z)
• Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models [63.36637269634553]
  We present a novel method of further improving performance by requiring models to compare multiple reasoning chains. We find that instruction tuning on DCoT datasets boosts the performance of even smaller, and therefore more accessible, language models.
  arXiv  Detail & Related papers  (2024-07-03T15:01:18Z)
• DANCE: Dual-View Distribution Alignment for Dataset Condensation [39.08022095906364]
  We propose a new DM-based method named Dual-view distribution AligNment for dataset CondEnsation (DANCE) Specifically, from the inner-class view, we construct multiple "middle encoders" to perform pseudo long-term distribution alignment. While from the inter-class view, we use the expert models to perform distribution calibration.
  arXiv  Detail & Related papers  (2024-06-03T07:22:17Z)
• LAMM: Label Alignment for Multi-Modal Prompt Learning [17.478967970736115]
  We introduce an innovative label alignment method named textbfLAMM, which can adjust the category embeddings of downstream datasets through end-to-end training. Our method significantly improves the performance of existing multi-modal prompt learning models in few-shot scenarios. Our methodology exhibits the preeminence in continual learning compared to other prompt tuning methods.
  arXiv  Detail & Related papers  (2023-12-13T15:29:52Z)
• Boundary Guided Learning-Free Semantic Control with Diffusion Models [44.37803942479853]
  We present our BoundaryDiffusion method for efficient, effective and light-weight semantic control with frozen pre-trained DDMs. We conduct extensive experiments on DPMs architectures (DDPM, iDDPM) and datasets (CelebA, CelebA-HQ, LSUN-church, LSUN-bedroom, AFHQ-dog) with different resolutions (64, 256)
  arXiv  Detail & Related papers  (2023-02-16T15:21:46Z)
• Cross-Modal Fine-Tuning: Align then Refine [83.37294254884446]
  ORCA is a cross-modal fine-tuning framework that extends the applicability of a single large-scale pretrained model to diverse modalities. We show that ORCA obtains state-of-the-art results on 3 benchmarks containing over 60 datasets from 12 modalities.
  arXiv  Detail & Related papers  (2023-02-11T16:32:28Z)
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
  We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
  arXiv  Detail & Related papers  (2022-10-11T08:24:50Z)
• Revisiting Consistency Regularization for Semi-Supervised Learning [80.28461584135967]
  We propose an improved consistency regularization framework by a simple yet effective technique, FeatDistLoss. Experimental results show that our model defines a new state of the art for various datasets and settings.
  arXiv  Detail & Related papers  (2021-12-10T20:46:13Z)
• An Adaptive Framework for Learning Unsupervised Depth Completion [59.17364202590475]
  We present a method to infer a dense depth map from a color image and associated sparse depth measurements. We show that regularization and co-visibility are related via the fitness of the model to data and can be unified into a single framework.
  arXiv  Detail & Related papers  (2021-06-06T02:27:55Z)
• Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data [87.61504710345528]
  We propose two strategies for freeing a neural network from tuning with OoD data, while improving its OoD detection performance. We specifically propose to decompose confidence scoring as well as a modified input pre-processing method. Our further analysis on a larger scale image dataset shows that the two types of distribution shifts, specifically semantic shift and non-semantic shift, present a significant difference.
  arXiv  Detail & Related papers  (2020-02-26T04:18:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.